Papers › YOLACT: Real-time Instance Segmentation

YOLACT: Real-time Instance Segmentation

4 Apr 2019ICCV 2019 10arXiv:1904.02689archive 2025-07-28

Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee

We present a simple, fully-convolutional model for real-time instance segmentation that achieves 29.8 mAP on MS COCO at 33.5 fps evaluated on a single Titan Xp, which is significantly faster than any previous competitive approach. Moreover, we obtain this result after training on only one GPU. We accomplish this by breaking instance segmentation into two parallel subtasks: (1) generating a set of prototype masks and (2) predicting per-instance mask coefficients. Then we produce instance masks by linearly combining the prototypes with the mask coefficients. We find that because this process doesn't depend on repooling, this approach produces very high-quality masks and exhibits temporal stability for free. Furthermore, we analyze the emergent behavior of our prototypes and show they learn to localize instances on their own in a translation variant manner, despite being fully-convolutional. Finally, we also propose Fast NMS, a drop-in 12 ms faster replacement for standard NMS that only has a marginal performance penalty.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (dbolya/yolact) is linked to this paper; the 21 samples below come from 5 community repositories. Syntology harvested code from dbolya/yolact for another paper.

dbolya/yolact: Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.

Syntology 21 code samples harvested from 5 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 5 repositories, 18 ran (11 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 11 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 18 samples that ran has no recorded date.

48 repositories listed; official and paper-mentioned ones first.

dbolya/yolact officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
Abhijeet8901/Instance-Segmentation-using-YOLACT mentioned on GitHubpytorchSyntology: 6 samples, 6 ran (4 instrument-failed) · 0 unverified report
BigThreeMI/Utils mentioned on GitHubtfSyntology: not harvested report
DataXujing/yolact_pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
DivaniMandi/myCustomDataset_yolact mentioned on GitHubpytorchSyntology: not harvested report
Hoang-it/orhcid_classification mentioned on GitHubSyntology: not harvested report
IntelligenceDatum/ICCV2019_Model_Compression mentioned on GitHubApache-2.0Syntology: not harvested report
Jittor/InstanceSegmentation-jittor mentioned on GitHubpytorchSyntology: not harvested report
KHKHG/yolact mentioned on GitHubpytorchMITSyntology: not harvested report
KevinJia1212/yolact_cityscapes_550 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
Ma-Dan/Yolact-CoreML mentioned on GitHubpytorchSyntology: not harvested report
NSCL/yolact_instance mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (2 instrument-failed) · 1 unverified report
SharifElfouly/easy-model-zoo mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientDet: Scalable and Efficient Object Detection (arXiv:1911.09070; that paper's own run record: 55 ran (of which 1 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
SpaceView/Yolact_EfficientNet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
Yahya1547/FaceMask mentioned on GitHubpytorchMITSyntology: not harvested report
YeshengSu/Yolact mentioned on GitHubpytorchMITSyntology: not harvested report
adityarc19/traffic-vehicles-instance-segmentation mentioned on GitHubpytorchSyntology: not harvested report
adityarc19/yolact-plus mentioned on GitHubpytorchSyntology: not harvested report
anshkumar/yolact mentioned on GitHubtfSyntology: not harvested report
artneer/yolact mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
banayoyo/yoolact mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
bihanli/yolactBH mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
divyachandana/yolact mentioned on GitHubpytorchMITSyntology: not harvested report
eddy4112/Yolact mentioned on GitHubpytorchMITSyntology: not harvested report
feiyuhuahuo/Yolact_minimal mentioned on GitHubpytorchSyntology: not harvested report
hakillha/yolact_yx mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
hampen2929/yolact mentioned on GitHubpytorchMITSyntology: not harvested report
hololee/YOLACT mentioned on GitHubpytorchSyntology: not harvested report
hyunahOh/instance_segmentation mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
hz-ants/yolact mentioned on GitHubpytorchMITSyntology: not harvested report
jiajunhua/dbolya-yolact mentioned on GitHubpytorchMITSyntology: not harvested report
kaylode/Clothes-Segmentation mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
kaylode/Trash-Segmentation mentioned on GitHubpytorchMITSyntology: not harvested report
lasithaya/yolact mentioned on GitHubpytorchMITSyntology: not harvested report
leenajyotishi/objectdetectionstuff mentioned on GitHubpytorchMITSyntology: not harvested report
leohsuofnthu/Tensorflow-YOLACT mentioned on GitHubtfSyntology: not harvested report
lucasfporto/yolactTest mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
skritik098/new_yolact mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLACT++: Better Real-time Instance Segmentation (arXiv:1912.06218; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
skritik098/new_yolact_2 mentioned on GitHubpytorchMITSyntology: not harvested report
songjmcn/yolact mentioned on GitHubpytorchMITSyntology: not harvested report
stuartchen1949/yolact-paddle mentioned on GitHubpaddleSyntology: not harvested report
youngwanLEE/CenterMask mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CenterMask : Real-Time Anchor-Free Instance Segmentation (arXiv:1911.06667; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zhaozhongch/yolact_ros mentioned on GitHubpytorchMITSyntology: not harvested report
zhawhjw/yolact-interpret mentioned on GitHubpytorchMITSyntology: not harvested report
zhhchen4njit/yolact mentioned on GitHubpytorchMITSyntology: not harvested report
zzuxzt/yolact_cpu mentioned on GitHubpytorchMITSyntology: not harvested report
jay-z20/yolact-paddle paddleSyntology: not harvested report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
4ran; the contract check could not run
8ran
3unverified

Licence: 9 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Abhijeet8901/Instance-Segmentation-using-YOLACT community (archive-listed) 6 samples, 6 ran (4 instrument-failed) · 0 unverified
clip_box utils/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7282c58e759e3dbe · report fixture: signature hw:tuple/1/int, boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-22
detect_collate coco.py ran · our draft was wrong no licence file found · pointer only · e70dc564949b6618 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-22
random_mirror in 7 papers utils/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 8d9436bf9882a717 · report fixture: signature img:ndarray/3/float, masks:ndarray/3/float, boxes:ndarray/2/float · returned tuple · level recorded 2026-09-22
remove_small_box utils/augmentations.py ran · honoured contract fingerprinted no licence file found · pointer only · eb86a8a082a54cfe · report fixture: signature boxes:Tensor/2/float, masks:Tensor/3/int, labels:Tensor/1/int, area_limit:int/0/int · returned tuple · level recorded 2026-09-22
train_collate coco.py ran · honoured contract no licence file found · pointer only · 1fc4ea983899e431 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-22
val_collate coco.py ran · our draft was wrong no licence file found · pointer only · b91f2cd5320db36f · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-22
NSCL/yolact_instance community (archive-listed) 8 samples, 7 ran (2 instrument-failed) · 1 unverified
center_size in 14 papers layers/box_utils.py ran MIT (permissive) · 0118ac3b2ad5818b · report fixture: returned Tensor · level recorded 2026-09-25
construct_backbone in 6 papers backbone.py ran MIT (permissive) · 87523070b15ff05c · report fixture: signature cfg:BackboneConfig/0/? · returned SimpleBackbone · level recorded 2026-09-25
do_nothing in 25 papers
census: 6 implementations from 9 papers, 1 distinct output on one shared input
utils/augmentations.py ran MIT (permissive) · 4b9f446ea18137b2 · report fixture: signature img:Tensor/4/float, masks:Tensor/4/int, boxes:Tensor/3/float, labels:Tensor/2/int · returned tuple · level recorded 2026-09-25
intersect in 33 papers utils/augmentations.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 6ec11ee890696819 · report fixture: signature box_a:ndarray/2/float, box_b:ndarray/1/float · returned ndarray · level recorded 2026-09-24
intersect in 33 papers layers/box_utils.py ran MIT (permissive) · 3e474dde8eaf6a0d · report fixture: returned Tensor · level recorded 2026-09-24
jaccard_numpy in 7 papers utils/augmentations.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 13675bf1f3f88001 · report fixture: signature box_a:ndarray/2/float, box_b:ndarray/1/float · returned ndarray · level recorded 2026-09-24
point_form in 15 papers layers/box_utils.py ran MIT (permissive) · 27dbfe70566c2e97 · report fixture: returned Tensor · level recorded 2026-09-25
darknetconvlayer backbone.py unverified MIT (permissive) · 901e174e8a74774c · report
artneer/yolact community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
center_size in 14 papers layers/box_utils.py ran fingerprinted MIT (permissive) · aa2475e010a1be13 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-24
intersect in 33 papers layers/box_utils.py ran fingerprinted MIT (permissive) · 958c2e3043ae1fcd · report fixture: signature box_a:Tensor/3/float, box_b:Tensor/3/float · returned Tensor · level recorded 2026-09-24
point_form in 15 papers layers/box_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 3bea1addc1e14162 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-22
banayoyo/yoolact community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
min utils/cython_nms.py ran fingerprinted MIT (permissive) · 2a5d0ff87f11c8d1 · report fixture: signature a:int/0/int, b:int/0/int · returned int · level recorded 2026-09-24
max utils/cython_nms.py unverified MIT (permissive) · 389a9dd64ec42965 · report
nms in 65 papers utils/cython_nms.py unverified MIT (permissive) · 19f521e775cbb114 · report
hakillha/yolact_yx community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
str2bool in 533 papers yolact_eval.py ran · violated contract MIT (permissive) · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded

Tasks

Instance SegmentationReal-time Instance SegmentationSegmentationSemantic SegmentationTranslation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival YOLACT-550 (ResNet-50) mask AP 29.9 #92 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev YOLACT (ResNet-50-FPN) mask AP 29.8% #104 of 112 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550 (ResNet-101-FPN) AP50 46.6 #20 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550 (ResNet-101-FPN) AP75 29.2 #20 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550 (ResNet-101-FPN) APL 44.8 #20 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550 (ResNet-101-FPN) APM 29.3 #20 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550 (ResNet-101-FPN) APS 9.2 #20 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550 (ResNet-101-FPN) Frame (fps) 33.3 (Titan Xp) #20 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550 (ResNet-101-FPN) mask AP 28.2 #20 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT AP50 42.0 #21 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT AP75 25.4 #21 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT APL 45.0 #21 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT APM 25.3 #21 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT APS 5.0 #21 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT Frame (fps) 45.3 (Titan Xp) #21 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT mask AP 24.9 #21 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections